Vehicle Data Transmission System Reducing Latency via Memory Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Advanced driver assistance systems (ADAS) and autonomous driving systems (ADS) face increased computational and resource overhead, latency, and security issues due to traditional multi-node systems, which hinder real-time control and safety in scenarios like emergency braking, and introduce synchronization and serialization challenges.
Innovation Solution
A data transmission system with a centralized controller and entities using a predefined data format for communication, employing smart pointers and communication channels to reduce overhead and latency, ensure data integrity and security, and synchronize data transmission, by allowing only authorized entities to access and modify data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional multi-node systems with publisher-subscriber pattern are used, then data exchange between nodes is enabled, but computational overhead and latency increase due to serialization and deserialization requirements
Solution Approach 1:
The patent merges the data structure and communication protocol into a single integrated memory-mapped structure. The data is stored in a predefined format that is directly accessible by multiple nodes without requiring serialization or deserialization, eliminating the time loss associated with these operations while maintaining efficient data exchange.
Solution Approach 2:
Instead of copying data through complex message formats and serializing it for transmission, the patent uses memory mapping to create direct references to shared data structures. This allows nodes to access the same data without copying it through intermediate formats, reducing latency and computational overhead.
2Adaptability or versatility
If predefined message formats are used for communication, then nodes can be programmed in different programming languages and communicate independently, but data integrity and security are compromised due to lack of access control
Solution Approach 1:
The patent applies local quality by assigning different access rights to different nodes based on their specific needs. Each node receives a unique access key that determines what data it can read or write, allowing language independence while maintaining data integrity through selective access control.
Solution Approach 2:
The patent introduces an intermediary access control mechanism in the form of access keys and permission checks. This mediator layer sits between the data structures and the nodes, verifying each access request before allowing data interaction, thus ensuring data integrity while preserving the ability to program nodes in different languages.
3Adaptability or versatility
If distributed nodes operate independently, then modularity and flexibility are improved, but synchronization of data access becomes difficult
Solution Approach 1:
The patent applies preliminary action by pre-defining the data structure format and memory mapping before nodes operate independently. This预先 setup ensures that all nodes understand the data layout in advance, allowing them to access and synchronize data without delays when operating independently with high modularity.
4Productivity
If multiple entities access shared data, then system functionality is enhanced, but computational resources are consumed for data preparation and decoding
Solution Approach 1:
The patent implements self-service by designing the data structure to be automatically interpreted by nodes through memory mapping. The data is prepared in the correct format at the source, and receiving nodes automatically access it without requiring computational resources for decoding or format conversion, thus reducing overall computational resource consumption while enhancing system functionality.
Data Source
AI summary
Provided is a data transmission system, a vehicle comprising the data transmission system, a data transmission method and a computer program. Specifically, the system comprises a centralized controller, a publisher entity and a subscriber entity; wherein the publisher entity and the subscriber entity are compiled with a predefined data format; the publisher entity registers at the centralized controller with topic information; the centralized controller, upon registration of the publisher entity, stores the topic information with information for registering at the publisher entity; the subscriber entity subscribes at the centralized controller to the topic information; the centralized controller, upon subscription of the subscriber entity, provides to the subscriber entity information for registering at the publisher entity; and the subscriber entity creates the communication channel between the publisher entity and the subscriber entity based on the information for registering at the publisher entity.